wix-cli-app-validation
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several shell commands to manage dependencies (npm install, yarn install, pnpm install), perform type checking (npx tsc), and build or preview the application (npx wix build, npx wix preview). These commands utilize the vendor's own CLI and standard development tools necessary for the stated validation purpose.
- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection by processing external data sources during its workflow. Ingestion points: The skill reads terminal output from the 'npx wix preview' command to extract URLs and reads the '.wix/debug.log' file for troubleshooting as described in SKILL.md. Boundary markers: No delimiters or protective markers are used to isolate this untrusted content from the agent's core instructions. Capability inventory: The skill possesses capabilities for file system access (cat, tail) and shell command execution. Sanitization: There is no evidence of sanitization or filtering of the ingested log data or command output before it is interpreted by the agent.
Audit Metadata